DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
All objections/rejections not mentioned in this Office Action have been withdrawn by the Examiner.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 22 July 2026 has been entered.
Status of the Claims
Prior to entry of the amendment(s) and/or consideration of the argument(s), the status of the claims is as follows.
Claim(s) 1-20 is/are pending.
Claims 9-14 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement.
Claims 9-14 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite.
Claim(s) 1, 2, 8, and 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah (U.S. Pat. App. Pub. No. 2025/0156455, hereinafter Subbiah) in view of Non-Patent Literature to Katsogiannis-Meimarakis (Katsogiannis-Meimarakis, G. and Koutrika, G., 2023. A survey on deep learning approaches for text-to-SQL. The VLDB Journal, 32(4), pp.905-936, hereinafter Katsogiannis).
Claims 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Katsogiannis as applied to claim 1 above, and further in view of Kar (U.S. Pat. App. Pub. No. 2025/0190802, hereinafter Kar).
Claims 4 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Katsogiannis as applied to claims 1 and 15 above, and further in view of Non-Patent Literature to Joachims (Joachims, T., Swaminathan, A. and Schnabel, T., 2017, February. Unbiased learning-to-rank with biased feedback. In Proceedings of the tenth ACM international conference on web search and data mining (pp. 781-789), hereinafter Joachims)
Claims 5-7, and 17-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Katsogiannis as applied to claim 1 above, and further in view of Chen (U.S. Pat. App. Pub. No. 2025/0077792, hereinafter Chen).
Claims 9, 11, and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah in view of Chen and Non-Patent Literature to Siriwardhana (Siriwardhana, S., Weerasekera, R., Wen, E., Kaluarachchi, T., Rana, R. and Nanayakkara, S., 2023. Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Transactions of the Association for Computational Linguistics, 11, pp.1-17., hereinafter Siriwardhana).
Claims 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah, Chen, and Siriwardhana as applied to claim 9 above, and further in view of Joachims.
Claims 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah, Chen, and Siriwardhana as applied to claim 9 above, and further in view of Zhan (CN112836068A, hereinafter Zhan).
Claims 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah, Chen, and Siriwardhana as applied to claim 9 above, and further in view of Non-Patent Literature to Xiong (Xiong, L., Xiong, C., Li, Y., Tang, K.F., Liu, J., Bennett, P., Ahmed, J. and Overwijk, A., 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808, hereinafter Xiong).
Claims 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Katsogiannis as applied to claim 15 above, and further in view of Chen and Mahajan (U.S. Pat. App. Pub. No. 2021/0026820, hereinafter Mahajan).
Response to Amendments
Applicant’s amendment filed on 22 July 2026 has been entered.
In view of the amendment to the claim(s), the amendment of claim(s) 1 and 8-15 have been acknowledged and entered.
In view of the amendment to claim(s) 9-14, the rejection of claims 9-14 under 35 U.S.C. §112 is withdrawn.
In view of the amendment to claim(s) 1 and 8-15, the rejection of claims 1-20 under 35 U.S.C. §102 and 103 is withdrawn.
In light of the amended claims, new grounds for rejection under 35 U.S.C. §103 are provided in the action below.
Response to Arguments
Applicant’s arguments regarding the prior art rejections under 35 U.S.C. §102/103, see pages 14-19 of the Response to Non-Final Office Action dated 12 May 2026, which was received on 22 July 2026 (hereinafter Response and Office Action, respectively), have been fully considered.
With respect to the rejection(s) of claim(s) 1 and 15 under 35 U.S.C. §103 in light of Subbiah in view of Katsogiannis, applicant asserts that the cited references fail to teach or suggest all limitations of amended claim 1 and 15. Applicant’s arguments are persuasive. Therefore, the rejection of claims 1 and 15 is withdrawn.
With respect to the rejection(s) of claim(s) 9 under 35 U.S.C. §103 in light of Subbiah in view of Katsogiannis, Kar and Chen, applicant asserts that the cited references fail to teach or suggest all limitations of amended claim 9. Applicant’s arguments are persuasive. Therefore, the rejection of claim 9 is withdrawn.
Applicant further argues that the rejection(s) of dependent claims 2-8, 10-14, and 16-20 should be withdrawn for at least the same reasons as independent claims 1, 9, and 15. Applicant’s arguments in light of the amended claims are persuasive. As such, the rejections of claims 2-8, 10-14, and 16-20 under 35 U.S.C. §103 are withdrawn.
However, upon further consideration, new ground(s) of rejection under 35 U.S.C. §103 are made in light of combinations of Subbiah, Kar, Chen, Joachims, Zhan, Xiong, and newly cited references Non-Patent Literature to Katsogiannis-Meimarakis (Katsogiannis-Meimarakis, G. and Koutrika, G., 2023. A survey on deep learning approaches for text-to-SQL. The VLDB Journal, 32(4), pp.905-936, hereinafter Katsogiannis) and Non-Patent Literature to Siriwardhana (Siriwardhana, S., Weerasekera, R., Wen, E., Kaluarachchi, T., Rana, R. and Nanayakkara, S., 2023. Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Transactions of the Association for Computational Linguistics, 11, pp.1-17., hereinafter Siriwardhana).
The Applicant has not provided any further statement and therefore, the Examiner directs the Applicant to the below rationale.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 2, 8-9, and 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah in view of Balasubramanian.
Regarding claim 1, Subbiah discloses A computer-implemented method comprising (Systems and methods described with reference to “using generative AI to process user queries in the construction domain”; Subbiah, ¶ [0105]): receiving a contextual query comprising terminology indicating a software context of a computer application within a software-specific domain (“At step 302, a user query is received/obtained (e.g., entered into a text dialog box and/or selected from a list of predefined queries) within a construction software system,” and the terminology can indicate a software context of a computer application (e.g., requests for information of RFIs received with regards to a construction application.); Subbiah, ¶ [0055], [0106]); mapping, using a context mapping model, ambiguous terminology in the contextual query to one or more context-specific terms… (“At step 304, a user query processing component may perform pre-processing of the user (NL) query including correcting typos, verifying the quality and safety of user input, and rephrasing and complementing user queries (i.e., to validate the query)” where “rephrasing and complementing user queries...to validate the query” is understood as resolving terminology in the query {contextual query}, and where the “rephrasing and complementing” includes “modify[ing] the query 402” such as by “generat[ing] general SQL queries that access relational datasets {...one or more context-specific terms}”; Subbiah, ¶ [0107], [0119], [0130]); extracting, using a context retrieval model..., a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents (“At step 306, an embedding model may then be utilized to embed the pre-processed text from the query into vectors for the semantic search” and “the semantic search is performed within each of the multiple different sections based on the search vectors and the stored vectors.”; Subbiah, ¶ [0108], [0111]); determining, using the context retrieval model, relevant digital documents from among the stored digital documents by comparing the query embedding and the plurality of data segment embeddings (“The semantic search identifies the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” by comparison between the “search vector and the stored vectors”; Subbiah, ¶ [0111]); and generating, from the relevant digital documents, a contextual response for the contextual query (“an LLM is utilized to generate a response based on the contextual data prompt,” where the contextual data prompt includes “the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” and the embeddings of “the pre-processed text from the query”; Subbiah, ¶ [0108], [0111], [0113]) utilizing a response generator model tuned to generate context-specific responses for the software contexts of the plurality of computer applications (Generative model as directed to “process[ing] user queries in the construction domain...within a construction software system” are fine-tuned and trained “to become more attuned to the construction industry’s evolving landscape” where the generative mode, which may also be a LLM, “the LLM is trained based on construction data and the response identifies the semantically relevant section(s)”; Subbiah, ¶ [0029], [0105]-[0106], [0108], [0113], [0120]). However, Subbiah fails to expressly recite one or more context-specific terms associated with the software context of the computer application within the software-specific domain; injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query; extracting, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents.
Balasubramanian teaches “methods and systems for searching software components based on user queries.” (Balasubramanian, ¶ [0002]). Regarding claim 1, Balasubramanian teaches mapping, using a context mapping model, ambiguous terminology in the contextual query to one or more context-specific terms (Further discloses “the Initial Query Entity Parser 104 {using a context mapping model} in communication with the Web GUI Portal 101 uses machine learning techniques to split the query into entities that pertain to software component technologies, framework terms, words that pertain to software component source code across multiple programming languages and words that pertain to natural language across multiple languages {...terminology in the contextual query}” and “the Technology Keyword Search Processor 105 in communication with the initial query entity parser 104 anchors the technology keyword enhancements” where the “Technology Keyword Search Processor 105 calls the Technology Keyword Service 106 to enhance the technology and framework keywords {mapping... to one or more context specific terms}.; Balasubramanian, ¶ [0057]-[0058]) associated with the software context of the computer application within the software-specific domain (“the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106 anchors the natural language keyword enhancements. The Natural Language Search Processor 107 calls the Editor and Classifier Service 108 to enhance the natural language keywords” which “uses machine learning techniques to enhance the natural language keywords present in the search query in the context of a software component search {associated with the software context of the computer application within the software-specific domain}.”; Balasubramanian, ¶ [0060]-[0061]); injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query (“The Technology Keyword Service 106 leverages the Software Taxonomy Crawler and Builder 112 to lookup relevant technology terms {the one or more context specific terms associated with the software context of the computer application within the software specific domain...}” where “The Technology Keyword Service 106 removes redundant terms, adds qualifiers, for example, version numbers, additional framework descriptors and prioritizes must have keywords critical to the search context and result.{injecting... into the contextual query}” and “the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106... calls the Editor and Classifier Service 108 to enhance the natural language keywords” which “removes redundant terms, identifies business and industry domains, completes and corrects terms, identifies the software component usage and intent using the appropriate verbs in the query and features requested through adjectives in the natural language.”; Balasubramanian, ¶ [0059], [0060]-[0061]); extracting, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents (“a transformer based natural language processing model {context retrieval model...} that is trained on the software technology dataset such as readme file, public technology question and answer website data {...trained to determine relevant contextual data for software contexts of a plurality of computer applications} is used to generate encoding vector {extracting... a query embedding} for a search query {...from the contextual query}” and which “produces an embedding vector for the given search query as output” “a transformer based natural language processing model... is used to generate encoding vector for a search query” and “The generated encoded vector is used to do semantic search and match in the search process,” where the semantic vector match includes generating embeddings from data segments of the search targets; Balasubramanian, ¶ [0079]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah to incorporate the teachings of Balasubramanian to include one or more context-specific terms associated with the software context of the computer application within the software-specific domain; injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query; extracting, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents. Balasubramanian discloses systems and methods for reducing the complexity of a search query by enhancing and splitting the query to perform individual searches in parallel to provide a more accurate search result, which will save significant time and eliminate any manual errors and oversight related to manual review of thousands or millions of search results, as recognized by Balasubramanian. (Balasubramanian, ¶ [0052]-[0053]).
Regarding claim 2, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein determining the relevant digital documents comprises: determining a context score for a stored digital document from among the stored digital documents based on comparing the query embedding and the plurality of data segment embeddings (“an optional information retrieval strategy is utilized to optimize information retrieval (e.g., in order to conduct a reliable semantic search)” which can include “a similarity score (e.g., utilized for measuring the text relevancy for the information retrieval)”; Subbiah, ¶ [0110]); and selecting the stored digital document as a relevant digital document based on the context score (In the optional embodiment, the similarity score is “utilized for measuring the text relevancy for the information retrieval” and the most relevant sections/text is selected; Subbiah, ¶ [0110]).
Regarding claim 8, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses [resolving ambiguous terminology in] the contextual query… (As explained above, the mapping of terminology to a software specific domain occurs at step 304 of Subbiah, where the “rephrasing and complementing user queries...to validate the query” is modified by the disambiguation techniques described in Balasubramanian in sections 2. and 2., to “resolving ambiguous terminology in the contextual query” as described above with relation to claim 1; Subbiah, ¶ [0107], [0119], [0130]) prior to generating the query embedding (“At step 306, an embedding model may then be utilized to embed the pre-processed text from the query into vectors for the semantic search” and “the semantic search is performed within each of the multiple different sections based on the search vectors and the stored vectors.” As such, the embedding occurs after the preprocessing {...prior to generating the query embedding}; Subbiah, ¶ [0108], [0111]). However, Subbiah fails to expressly recite wherein injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query comprises modifying the contextual query to align the terminology with a software-specific domain representation prior to generating the query embedding.
The relevance of Balasubramanian is described above with relation to claim 1. Regarding claim 8, Balasubramanian teaches wherein injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query comprises modifying the contextual query to align the terminology with a software-specific domain representation (As indicated above “the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106... calls the Editor and Classifier Service 108 to enhance the natural language keywords {modifying the contextual query...}” which includes “identif[ying] the software component usage and intent using the appropriate verbs in the query and features requested through adjectives in the natural language {...to align the terminology with a software-specific domain representation}” all of which is part of the initial parsing, shown in FIG. 3 at 302 as the initial parsing and explained in greater detail at FIG. 4.; Balasubramanian, ¶ [0059], [0060]-[0061]; FIG. 3 and 4) prior to generating the query embedding (the “transformer based natural language processing model... is used to generate encoding vector for a search query” producing “an embedding vector for the given search query as output” where said embedding is generated at step 304 of FIG. 3, which occurs after 302. Therefore, the initial parsing at 302 occurs prior to generating the query embedding at 304.; Balasubramanian, ¶ [0079], FIG. 3 and 7).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah to incorporate the teachings of Balasubramanian to include wherein injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query comprises modifying the contextual query to align the terminology with a software-specific domain representation prior to generating the query embedding. Balasubramanian discloses systems and methods for reducing the complexity of a search query by enhancing and splitting the query to perform individual searches in parallel to provide a more accurate search result, which will save significant time and eliminate any manual errors and oversight related to manual review of thousands or millions of search results, as recognized by Balasubramanian. (Balasubramanian, ¶ [0052]-[0053]).
Regarding claim 9, Subbiah discloses A non-transitory computer readable medium storing executable instructions which, when executed by a processing device, cause the processing device to perform operations comprising (Systems and methods described with reference to “using generative AI to process user queries in the construction domain” which may be “tangibly embodied in a non-transitory computer-readable medium” as implemented using a “computer 902” including a “processor 904” and a “memory 906” where “the operating system 908 and the computer program 910 are comprised of computer program 910 instructions which, when accessed, read and executed by the computer 902, cause the computer 902 to perform the steps necessary to implement and/or use the present invention”; Subbiah, ¶ [0105], [0140], [0147]): receiving a contextual query comprising terminology indicating a software context of a computer application within a software-specific domain (“At step 302, a user query is received/obtained (e.g., entered into a text dialog box and/or selected from a list of predefined queries) within a construction software system,” and the terminology can indicate a software context of a computer application (e.g., requests for information of RFIs received with regards to a construction application.); Subbiah, ¶ [0055], [0106]); mapping, using a context mapping model, one or more ambiguous terms in the contextual query to one or more context-specific terms… (“At step 304, a user query processing component may perform pre-processing of the user (NL) query including correcting typos, verifying the quality and safety of user input, and rephrasing and complementing user queries (i.e., to validate the query)” {mapping... ambiguous terms} where “rephrasing and complementing user queries...to validate the query” is understood as resolving terminology in the query {contextual query}, and where the “rephrasing and complementing” includes “modify[ing] the query 402” such as by “generat[ing] general SQL queries that access relational datasets {...one or more context-specific terms}”; Subbiah, ¶ [0107], [0119], [0130]); extracting, using a context retrieval model..., a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents (“At step 306, an embedding model may then be utilized to embed the pre-processed text from the query into vectors for the semantic search” and “the semantic search is performed within each of the multiple different sections based on the search vectors and the stored vectors.”; Subbiah, ¶ [0108], [0111]); determining, using the context retrieval model, relevant digital documents from among the stored digital documents by comparing the query embedding and the plurality of data segment embeddings (“The semantic search identifies the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” by comparison between the “search vector and the stored vectors”; Subbiah, ¶ [0111]); and generating, from the relevant digital documents, a contextual response for the contextual query (“an LLM is utilized to generate a response based on the contextual data prompt,” where the contextual data prompt includes “the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” and the embeddings of “the pre-processed text from the query”; Subbiah, ¶ [0108], [0111], [0113]) utilizing a response generator model tuned to generate context-specific responses for the software contexts of the plurality of computer applications (Generative model as directed to “process[ing] user queries in the construction domain...within a construction software system” are fine-tuned and trained “to become more attuned to the construction industry’s evolving landscape” where the generative mode, which may also be a LLM, “the LLM is trained based on construction data and the response identifies the semantically relevant section(s)”; Subbiah, ¶ [0029], [0105]-[0106], [0108], [0113], [0120]). However, Subbiah fails to expressly recite one or more context-specific terms associated with the software context of the computer application within the software-specific domain; injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query; extracting, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents.
The relevance of Balasubramanian is described above with relation to claim 1. Regarding claim 9, Balasubramanian teaches mapping, using a context mapping model, one or more ambiguous terms in the contextual query to one or more context-specific terms (Further discloses “the Initial Query Entity Parser 104 {using a context mapping model} in communication with the Web GUI Portal 101 uses machine learning techniques to split the query into entities that pertain to software component technologies, framework terms, words that pertain to software component source code across multiple programming languages and words that pertain to natural language across multiple languages” where said terms are ambiguous, at least as compared to proposed enhancements {...ambiguous terms in the contextual query} and “the Technology Keyword Search Processor 105 in communication with the initial query entity parser 104 anchors the technology keyword enhancements” where the “Technology Keyword Search Processor 105 calls the Technology Keyword Service 106 to enhance the technology and framework keywords {mapping... to one or more context specific terms}.; Balasubramanian, ¶ [0057]-[0058]) associated with the software context of the computer application within the software-specific domain (“the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106 anchors the natural language keyword enhancements. The Natural Language Search Processor 107 calls the Editor and Classifier Service 108 to enhance the natural language keywords” which “uses machine learning techniques to enhance the natural language keywords present in the search query in the context of a software component search {associated with the software context of the computer application within the software-specific domain}.”; Balasubramanian, ¶ [0060]-[0061]); injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query (“The Technology Keyword Service 106 leverages the Software Taxonomy Crawler and Builder 112 to lookup relevant technology terms {the one or more context specific terms associated with the software context of the computer application within the software specific domain...}” where “The Technology Keyword Service 106 removes redundant terms, adds qualifiers, for example, version numbers, additional framework descriptors and prioritizes must have keywords critical to the search context and result.{injecting... into the contextual query}” and “the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106... calls the Editor and Classifier Service 108 to enhance the natural language keywords” which “removes redundant terms, identifies business and industry domains, completes and corrects terms, identifies the software component usage and intent using the appropriate verbs in the query and features requested through adjectives in the natural language.”; Balasubramanian, ¶ [0059], [0060]-[0061]); extracting, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents (“a transformer based natural language processing model {context retrieval model...} that is trained on the software technology dataset such as readme file, public technology question and answer website data {...trained to determine relevant contextual data for software contexts of a plurality of computer applications} is used to generate encoding vector {extracting... a query embedding} for a search query {...from the contextual query}” and which “produces an embedding vector for the given search query as output” “a transformer based natural language processing model... is used to generate encoding vector for a search query” and “The generated encoded vector is used to do semantic search and match in the search process,” where the semantic vector match includes generating embeddings from data segments of the search targets; Balasubramanian, ¶ [0079]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah to incorporate the teachings of Balasubramanian to include one or more context-specific terms associated with the software context of the computer application within the software-specific domain; injecting the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query; extracting, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents. Balasubramanian discloses systems and methods for reducing the complexity of a search query by enhancing and splitting the query to perform individual searches in parallel to provide a more accurate search result, which will save significant time and eliminate any manual errors and oversight related to manual review of thousands or millions of search results, as recognized by Balasubramanian. (Balasubramanian, ¶ [0052]-[0053]).
Regarding claim 15, Subbiah discloses A system comprising: one or more memory devices; and one or more processors coupled to the one or more memory devices (Systems and methods described with reference to “using generative AI to process user queries in the construction domain” which may be “tangibly embodied in a non-transitory computer-readable medium” as part of a “computer 902” including a “processor 904” and a “memory 906” coupled to said processor 904, where “the operating system 908 and the computer program 910 are comprised of computer program 910 instructions which, when accessed, read and executed by the computer 902, cause the computer 902 to perform the steps necessary to implement and/or use the present invention”; Subbiah, ¶ [0105], [0140], [0147]), the one or more processors configured to cause the system to: receive a contextual query comprising terminology indicating a software context of a computer application (“At step 302, a user query is received/obtained (e.g., entered into a text dialog box and/or selected from a list of predefined queries) within a construction software system,” and the terminology can indicate a software context of a computer application (e.g., requests for information of RFIs received with regards to a construction application.); Subbiah, ¶ [0055], [0106]); map, using a context mapping model, ambiguous terminology in the contextual query to one or more context-specific terms… (“At step 304, a user query processing component may perform pre-processing of the user (NL) query including correcting typos, verifying the quality and safety of user input, and rephrasing and complementing user queries (i.e., to validate the query)” where “rephrasing and complementing user queries...to validate the query” is understood as resolving terminology in the query {contextual query}, and where the “rephrasing and complementing” includes “modify[ing] the query 402” such as by “generat[ing] general SQL queries that access relational datasets {...one or more context-specific terms}”; Subbiah, ¶ [0107], [0119], [0130]); extract, using a context retrieval model..., a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents (“At step 306, an embedding model may then be utilized to embed the pre-processed text from the query into vectors for the semantic search” and “the semantic search is performed within each of the multiple different sections based on the search vectors and the stored vectors.”; Subbiah, ¶ [0108], [0111]); determine, using the context retrieval model, relevant digital documents from among the stored digital documents by comparing the query embedding and the plurality of data segment embeddings (“The semantic search identifies the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” by comparison between the “search vector and the stored vectors”; Subbiah, ¶ [0111]); and generate, from the relevant digital documents, a contextual response for the contextual query (“an LLM is utilized to generate a response based on the contextual data prompt,” where the contextual data prompt includes “the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” and the embeddings of “the pre-processed text from the query”; Subbiah, ¶ [0108], [0111], [0113]) utilizing a response generator model tuned to generate context-specific responses for the software contexts of the plurality of computer applications (Generative model as directed to “process[ing] user queries in the construction domain...within a construction software system” are fine-tuned and trained “to become more attuned to the construction industry’s evolving landscape” where the generative mode, which may also be a LLM, “the LLM is trained based on construction data and the response identifies the semantically relevant section(s)”; Subbiah, ¶ [0029], [0105]-[0106], [0108], [0113], [0120]). However, Subbiah fails to expressly recite one or more context-specific terms associated with the software context of the computer application within the software-specific domain; inject the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query; extract, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents.
The relevance of Balasubramanian is described above with relation to claim 1. Regarding claim 15, Balasubramanian teaches map, using a context mapping model, ambiguous terminology in the contextual query to one or more context-specific terms (Further discloses “the Initial Query Entity Parser 104 {using a context mapping model} in communication with the Web GUI Portal 101 uses machine learning techniques to split the query into entities that pertain to software component technologies, framework terms, words that pertain to software component source code across multiple programming languages and words that pertain to natural language across multiple languages {...terminology in the contextual query}” and “the Technology Keyword Search Processor 105 in communication with the initial query entity parser 104 anchors the technology keyword enhancements” where the “Technology Keyword Search Processor 105 calls the Technology Keyword Service 106 to enhance the technology and framework keywords {mapping... to one or more context specific terms}.; Balasubramanian, ¶ [0057]-[0058]) associated with the software context of the computer application within the software-specific domain (“the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106 anchors the natural language keyword enhancements. The Natural Language Search Processor 107 calls the Editor and Classifier Service 108 to enhance the natural language keywords” which “uses machine learning techniques to enhance the natural language keywords present in the search query in the context of a software component search {associated with the software context of the computer application within the software-specific domain}.”; Balasubramanian, ¶ [0060]-[0061]); inject the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query (“The Technology Keyword Service 106 leverages the Software Taxonomy Crawler and Builder 112 to lookup relevant technology terms {the one or more context specific terms associated with the software context of the computer application within the software specific domain...}” where “The Technology Keyword Service 106 removes redundant terms, adds qualifiers, for example, version numbers, additional framework descriptors and prioritizes must have keywords critical to the search context and result.{injecting... into the contextual query}” and “the Natural Language Search Processor 107 in communication with the Technology Keyword Service 106... calls the Editor and Classifier Service 108 to enhance the natural language keywords” which “removes redundant terms, identifies business and industry domains, completes and corrects terms, identifies the software component usage and intent using the appropriate verbs in the query and features requested through adjectives in the natural language.”; Balasubramanian, ¶ [0059], [0060]-[0061]); extract, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents (“a transformer based natural language processing model {context retrieval model...} that is trained on the software technology dataset such as readme file, public technology question and answer website data {...trained to determine relevant contextual data for software contexts of a plurality of computer applications} is used to generate encoding vector {extracting... a query embedding} for a search query {...from the contextual query}” and which “produces an embedding vector for the given search query as output” “a transformer based natural language processing model... is used to generate encoding vector for a search query” and “The generated encoded vector is used to do semantic search and match in the search process,” where the semantic vector match includes generating embeddings from data segments of the search targets; Balasubramanian, ¶ [0079]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah to incorporate the teachings of Balasubramanian to include one or more context-specific terms associated with the software context of the computer application within the software-specific domain; inject the one or more context-specific terms associated with the software context of the computer application within the software-specific domain into the contextual query; extract, using a context retrieval model trained to determine relevant contextual data for software contexts of a plurality of computer applications, a query embedding from the contextual query and a plurality of data segment embeddings from data segments of stored digital documents. Balasubramanian discloses systems and methods for reducing the complexity of a search query by enhancing and splitting the query to perform individual searches in parallel to provide a more accurate search result, which will save significant time and eliminate any manual errors and oversight related to manual review of thousands or millions of search results, as recognized by Balasubramanian. (Balasubramanian, ¶ [0052]-[0053]).
Regarding claim 16, the rejection of claim 15 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the one or more processors are further configured to cause the system to extract the plurality of data segment embeddings by: dividing content of the stored digital documents into the semantically consistent segments (“an optional information retrieval strategy is utilized to optimize information retrieval (e.g., in order to conduct a reliable semantic search)” which “may include the use of: (a) a chunking method (e.g., a method to chunk a document into text segments)”; Subbiah, ¶ [0110]) by determining content portions associated with one or more semantic concepts (“Optimization strategies” can further include “(b) a similarity score (e.g., utilized for measuring the text relevancy for the information retrieval)” and “(d) a searching strategy (e.g., a method to determining where to search and what chunks to retrieve); Subbiah, ¶ [0110]); and utilize the context retrieval model to encode a data segment embedding from a semantically consistent segment (“Optimization strategies” can further include “(c) retrievers (e.g., an algorithm utilized for retrieving relevant texts searching strategy”; Subbiah, ¶ [0110]).
Claims 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Balasubramanian as applied to claim 1 above, and further in view of Kar.
Regarding claim 3, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the context retrieval model is a…[machine] learning model (Embedding model is “trained based on construction data and the response identifies the semantically relevant section(s)” which is a machine learning model.; Subbiah, ¶ [0029], [0105]-[0106], [0108], [0113], [0120]) trained to determine, from among help documents, community question records, and help video transcripts, relevant data segments corresponding to the software contexts of the plurality of computer applications (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records.; Subbiah, ¶ [0023], [0029]). However, Subbiah fails to expressly recite wherein the context retrieval model is a contrastive learning model.
Kar teaches systems and methods for “contrastive learning of contextual retrieval augmented generation using semi-supervised retriever.” (Kar, ¶ [0001]). Regarding claim 3, Kar teaches wherein the context retrieval model is a contrastive learning model (discloses the source data for training as “A large corpus of unlabeled text data containing questions and their corresponding contexts” which comprises user questions and associated context is stored user interaction logs and stored digital documents, and the system generates a “plurality of positive and negative query-context pairs for the unlabeled text and the corresponding context”; Kar, ¶ [0031], [0051]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Kar to include wherein the context retrieval model is a contrastive learning model. “Self-supervised learning, when combined with retrieval-based architectures like Dense Passage Retriever,” as described in Kar, “enables fast and efficient retrieval of relevant passages, improving system response times and user experience,” which allows the system to reduce hallucinations and improve “retrieval speed without sacrificing the quality of results” generated by the generative model, as recognized by Kar. (Kar, ¶ [0011], [0094]-[0095]).
Claims 4, 10 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Balasubramanian as applied to claims 1, 9, and 15 above, and further in view of Joachims.
Regarding claim 4, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the context retrieval model is trained by: identifying a set of digital documents associated with client device interaction in relation to a sample query (“both Generative and Embedding models, including Language Models (LLMs), are fine-tuned and trained” by “iterative refinement” using “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops” such that they “become more effective in surfacing relevant information to customers” where “LLM is utilized to generate a response based on the contextual data prompt {a sample query}. In this regard, the LLM is trained based on construction data and the response identifies the semantically relevant section(s) {identifying a set of digital documents associated with client device interaction}” and discloses iterative refinement using documents including “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” each of which are digital documents which are associated with a client device interaction, and as they are related to iterative refinement using “the wealth of data generated during construction projects” the interaction is with relation to a sample query.; Subbiah, ¶ [0023], [0029], [0111]-[0113]). However, Subbiah fails to expressly recite determining, for a sample digital document from among the set of digital documents, a relevance metric in relation to the sample query based on comparing a selection total of the sample digital document and selection totals of other sample documents in the set of digital documents; and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric.
Joachims teaches systems and methods for “Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback,. (Joachims, Abstract). Regarding claim 4, Joachims teaches determining, for a sample digital document from among the set of digital documents, a relevance metric in relation to the sample query (Discloses training on “Implicit feedback (e.g., clicks, dwell times, etc.)” in the context of a user submitting a query and interacting with a ranked list of documents, based on a “probability value” referred to “as the propensity of the observation” based on interactions with “search rankings” “search results” and a “given query”; Joachims, ¶ Abstract, p. 783, col. 1, para. 3) based on comparing a selection total of the sample digital document and selection totals of other sample documents in the set of digital documents (generating the propensity estimation includes swapping “the result at rank k with the result at rank r” and then calculating the ratio of “observed click-through rates (CTR)” where the ratio of CTR is the claimed comparison of selection totals.; Joachims, ¶ p. 785, col. 1, paras. 2-3); and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric (Further discloses “Empirical Risk Minimization (ERM)” disclosing “modifying parameters” by minimizing a “loss function,” where the loss function is explicitly weighted by the propensity to “derive a Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback” and authors explicitly consider a cross entropy loss function in their future directions (a “propensity ERM approach” can be developed for “pointwise LTR” and “listwise LTR,” where listwise LTR incorporate cross entropy loss as the loss function.; Joachims, ¶ abstract; p. 782, col. 1, para. 4, p. 788, col. 2, para. 6).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Joachims to include determining, for a sample digital document from among the set of digital documents, a relevance metric in relation to the sample query based on comparing a selection total of the sample digital document and selection totals of other sample documents in the set of digital documents; and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric. Joachims discloses a “Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback” which “allows training of ranking functions even in settings where queries do not repeat” and the authors show “empirically that the proposed learning method is highly effective in dealing with biases, that it is robust to noise and propensity model misspecification, and that it scales efficiently” while real-world analysis shows substantial improvement in retrieval performance, as recognized by Joachims. (Joachims, Abstract).
Regarding claim 10, the rejection of claim 9 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the context retrieval model is trained by: identifying a set of digital documents associated with client device interaction in relation to the sample query (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents including “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” each of which are digital documents which are associated with a client device interaction, and as they are related to iterative refinement using “the wealth of data generated during construction projects” the interaction is with relation to a sample query.; Subbiah, ¶ [0023], [0029]). However, Subbiah fails to expressly recite determining, for a sample digital document from among the set of digital documents, a relevance metric based on comparing selections of the sample digital document and selections of other sample documents in the set of digital documents; and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric.
The relevance of Joachims is described above with relation to claim 4. Regarding claim 10, Joachims teaches determining, for a sample digital document from among the set of digital documents, a relevance metric (Discloses training on “Implicit feedback (e.g., clicks, dwell times, etc.)” in the context of a user submitting a query and interacting with a ranked list of documents, based on a “probability value” referred to “as the propensity of the observation” based on interactions with “search rankings” “search results” and a “given query”; Joachims, ¶ Abstract, p. 783, col. 1, para. 3) based on comparing selections of the sample digital document and selections of other sample documents in the set of digital documents (generating the propensity estimation includes swapping “the result at rank k with the result at rank r” and then calculating the ratio of “observed click-through rates (CTR)” where the ratio of CTR is the claimed comparison of selection totals.; Joachims, ¶ p. 785, col. 1, paras. 2-3); and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric (Further discloses “Empirical Risk Minimization (ERM)” disclosing “modifying parameters” by minimizing a “loss function,” where the loss function is explicitly weighted by the propensity to “derive a Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback” and authors explicitly consider a cross entropy loss function in their future directions (a “propensity ERM approach” can be developed for “pointwise LTR” and “listwise LTR,” where listwise LTR incorporate cross entropy loss as the loss function.; Joachims, ¶ abstract; p. 782, col. 1, para. 4, p. 788, col. 2, para. 6).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Joachims to include determining, for a sample digital document from among the set of digital documents, a relevance metric based on comparing selections of the sample digital document and selections of other sample documents in the set of digital documents; and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric. Joachims discloses a “Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback” which “allows training of ranking functions even in settings where queries do not repeat” and the authors show “empirically that the proposed learning method is highly effective in dealing with biases, that it is robust to noise and propensity model misspecification, and that it scales efficiently” while real-world analysis shows substantial improvement in retrieval performance, as recognized by Joachims. (Joachims, Abstract).
Regarding claim 20, the rejection of claim 15 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the context retrieval model is trained by: identifying a set of digital documents selected via client device interaction in relation to a sample query (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents including “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” each of which are digital documents which are selected by the system for the iterative refinement via a client device interaction, and as they are related to iterative refinement using “the wealth of data generated during construction projects,” the interaction is with relation to a sample query.; Subbiah, ¶ [0023], [0029]). However, Subbiah fail(s) to expressly recite determining, for a sample digital document from among the set of digital documents, a relevance metric in relation to the sample query based on comparing a selection total of the sample digital document and selection totals of other sample documents in the set of digital documents; and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric.
The relevance of Joachims is described above with relation to claim 4. Regarding claim 20, Joachims teaches determining, for a sample digital document from among the set of digital documents, a relevance metric in relation to the sample query (Discloses training on “Implicit feedback (e.g., clicks, dwell times, etc.)” in the context of a user submitting a query and interacting with a ranked list of documents, based on a “probability value” referred to “as the propensity of the observation” based on interactions with “search rankings” “search results” and a “given query”; Joachims, ¶ Abstract, p. 783, col. 1, para. 3) based on comparing a selection total of the sample digital document and selection totals of other sample documents in the set of digital documents (generating the propensity estimation includes swapping “the result at rank k with the result at rank r” and then calculating the ratio of “observed click-through rates (CTR)” where the ratio of CTR is the claimed comparison of selection totals.; Joachims, ¶ p. 785, col. 1, paras. 2-3); and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric (Further discloses “Empirical Risk Minimization (ERM)” disclosing “modifying parameters” by minimizing a “loss function,” where the loss function is explicitly weighted by the propensity to “derive a Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback” and authors explicitly consider a cross entropy loss function in their future directions (a “propensity ERM approach” can be developed for “pointwise LTR” and “listwise LTR,” where listwise LTR incorporate cross entropy loss as the loss function.; Joachims, ¶ abstract; p. 782, col. 1, para. 4, p. 788, col. 2, para. 6).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Joachims to include determining, for a sample digital document from among the set of digital documents, a relevance metric in relation to the sample query based on comparing a selection total of the sample digital document and selection totals of other sample documents in the set of digital documents; and modifying parameters of the context retrieval model using a cross entropy loss function weighted according to the relevance metric. Joachims discloses a “Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback” which “allows training of ranking functions even in settings where queries do not repeat” and the authors show “empirically that the proposed learning method is highly effective in dealing with biases, that it is robust to noise and propensity model misspecification, and that it scales efficiently” while real-world analysis shows substantial improvement in retrieval performance, as recognized by Joachims. (Joachims, Abstract).
Claims 5-7, 11, 14, and 17-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Balasubramanian as applied to claims 1, 9, and 15 above, and further in view of Chen.
Regarding claim 5, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses further comprising: determining a relevant question-answer pair in relation to the contextual query from among a plurality of question-answer pairs generated utilizing a large language model (Discloses that the user query into “search vectors for a semantic search,” where search vectors are searched against stored vectors, and “an exemplary vector store may include the issues vector database 608A, a specs vector database 608B, and a submittals vector database 608C (collectively referred to as vector store/database 608),” and where “the semantic search is performed within each of the multiple different sections based on the search vectors and the stored vectors. The semantic search identifies the semantically relevant sections of the multiple different sections” and “vector store may be utilized as a dedicated repository for storing embedding vectors that are associated with specification chunks”; Subbiah, ¶ [0111], [0122]-[0123]) tuned based on the stored digital documents, wherein the stored digital documents comprise help documents, community question records, and... [unstructured data] (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records. Further discloses a process including “asking and answering of complex questions directly within construction documents” and “the process is bolstered by custom preprocessing algorithms designed to extract and index information” such as from “unstructured document”; Subbiah, ¶ [0023], [0029]); and generating the contextual response utilizing the response generator model prompted using the relevant question-answer pair (“an LLM is utilized to generate a response based on the contextual data prompt,” where the contextual data prompt includes “the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” and the embeddings of “the pre-processed text from the query”; Subbiah, ¶ [0108], [0111], [0113]). However, Subbiah fails to expressly recite wherein the unstructured data includes help video transcripts.
Chen teaches systems and methods for the fine tuning of machine learning models. (Chen, ¶ [0001]). Regarding claim 5, Chen teaches wherein the unstructured data includes help video transcripts (Discloses that the “domain specific training document is an unstructured data” which can include “video files”, where video files includes help video files, and where “machine-generated text of a content type” is “extracted from the domain-specific training document.” Thus unstructured data also includes help video transcripts.; Chen, ¶ [0132], [0139]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include wherein the unstructured data includes help video transcripts. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Regarding claim 6, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the response generator model comprises parameters learned by: generating a question-answer pair... utilizing a large language model (“an LLM is utilized to generate a response based on the contextual data prompt” where the contextual data prompt comprises “the semantically relevant sections (identified in the semantic search) are consolidated/aggregated (e.g., based on relevancy) into a contextual data prompt” alongside the user query, where the generative model is an LLM “trained {to learn...}based on construction data and the response identifies the semantically relevant section(s) {relevant digital documents for the respective software contexts of the computer applications}”; Subbiah, ¶ [0112]-[0113]) tuned based on the stored digital documents, wherein the stored digital documents comprise help documents, community question records, and… [unstructured data] (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models' understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records. Further discloses a process including “asking and answering of complex questions directly within construction documents” and “the process is bolstered by custom preprocessing algorithms designed to extract and index information” such as from “unstructured document”; Subbiah, ¶ [0023], [0027], [0029]). However, Subbiah fails to expressly recite generating a question-answer pair from a ground truth document utilizing a large language model tuned based on the stored digital documents; generating a predicted response for a sample question from the question-answer pair utilizing the response generator model prompted by the sample question, the ground truth document, and a negative document; and refining the parameters based on a comparison of the predicted response to an answer corresponding to the sample question within the question-answer pair; and wherein the unstructured data includes help video transcripts.
The relevance of Chen is described above with relation to claim 5. Regarding claim 6, Chen teaches generating a question-answer pair from a ground truth document utilizing a large language model tuned based on the stored digital documents (Discloses a training data generator to generate input-output pairs, where the “training component 152 uses the manual input-output pairs 104 to train 154 the training data generator 156” as well as obtained “content items 108 by querying the storage system 140, and receiving, from the storage system 140, content items 160” and, in some examples, “the training data generator 156 trained by the training component 152 is an LLM”; Chen, ¶ [0040]-[0041]); generating a predicted response for a sample question from the question-answer pair utilizing the response generator model prompted by the sample question, the ground truth document, and a negative document (“In the second stage of the training pipeline, a second machine learning model” also referred to as “pretrained machine learning model 408,” is “fine-tuned to perform one or more domain-specific tasks using the generated supplemental training data” where the generated supplemental training data includes “An input-output pair (e.g., training input 402 and corresponding pseudo label 418, determined by the training data generator 256 described in FIG. 2)” which is “an input with an associated output” and includes “a predicted output and an actual output”; Chen, ¶ [0025], [0060], [0062], [0064]); and refining the parameters based on a comparison of the predicted response to an answer corresponding to the sample question within the question-answer pair (“During each training iteration, the weights are tuned to reduce the amount of error thereby minimizing the differences between (or otherwise converging) a predicted output and an actual output” and “the fine-tuning manager 430 fine-tunes the weights in the pretrained machine learning model 408” where “the value of the pretrained weights in the pretrained weight matrix is adjusted according to an error (e.g., the error 412 determined by the comparator 410 comparing the pseudo label 418 to the predicted output 406).”; Chen, ¶ [0060], [0070]); and wherein the unstructured data includes help video transcripts (Discloses that the “domain specific training document is an unstructured data” which can include “video files”, where video files includes help video files, and where “machine-generated text of a content type” is “extracted from the domain-specific training document.” Thus unstructured data also includes help video transcripts.; Chen, ¶ [0132], [0139]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include generating a question-answer pair from a ground truth document utilizing a large language model tuned based on the stored digital documents; generating a predicted response for a sample question from the question-answer pair utilizing the response generator model prompted by the sample question, the ground truth document, and a negative document; and refining the parameters based on a comparison of the predicted response to an answer corresponding to the sample question within the question-answer pair; and wherein the unstructured data includes help video transcripts. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Regarding claim 7, the rejection of claim 1 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. However, Subbiah fails to expressly recite wherein the response generator model comprises parameters learned by: generating a negative response for a sample question utilizing the response generator model prompted by the sample question and a negative document, wherein the negative response indicates that no answer is found within the stored digital documents; and refining the parameters based on the negative response.
The relevance of Chen is described above with relation to claim 5. Regarding claim 7, Chen teaches wherein the response generator model comprises parameters learned by: generating a negative response for a sample question utilizing the response generator model prompted by the sample question and a negative document, (“the fine-tuning manager 430 can fine-tune the pretrained machine learning model 408 using negative samples. In some embodiments, negative training samples are obtained by the training data generator 156. For example, negative samples may be part of the input-output training pairs that are provided to fine-tune the pretrained machine learning model 408.”; Chen, ¶ [0083]) wherein the negative response indicates that no answer is found within the stored digital documents (“Fine-tuning the pretrained machine learning model 408 using negative samples allows the fine-tuned machine learning model 425 to identify when there is not a concept to be extracted from a sample. For example, given the phrase “today is a sunny day,” and the task to extract a skill, the fine-tuned machine learning model 425 would return “None” because there is no skill to be extracted from the phrase ‘today is a sunny day’.”; Chen, ¶ [0083]); and refining the parameters based on the negative response (The pretrained machine learning model is finetuned {refining the parameters} based on the negative samples {the negative response}; Chen, ¶ [0083]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include wherein the response generator model comprises parameters learned by: generating a negative response for a sample question utilizing the response generator model prompted by the sample question and a negative document, wherein the negative response indicates that no answer is found within the stored digital documents; and refining the parameters based on the negative response. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Regarding claim 11, the rejection of claim 9 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the operations further comprise: generating question-answer pairs from a ground truth document utilizing a large language model to process the stored digital documents, (“an LLM is utilized to generate a response based on the contextual data prompt” where the contextual data prompt comprises “the semantically relevant sections (identified in the semantic search) are consolidated/aggregated (e.g., based on relevancy) into a contextual data prompt” alongside the user query, where the generative model is an LLM “trained {to learn...} based on construction data and the response identifies the semantically relevant section(s) {relevant digital documents for the respective software contexts of the computer applications}” and where the question-answer pairs can further comprise “ground-truth data”. (e.g., “evaluation of the system may not be a perfect process against 100% true ground-truth data” which indicates a standard supervised learning question-answer pair including a prompt for “evaluation of the system” and a ground truth output to be compared to the output of the system, determine loss, and update the system to compensate for the loss); Subbiah, ¶ [0112]-[0113]) wherein the stored digital documents comprise help documents, community question records, and [unstructured data] (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records. Further discloses a process including “asking and answering of complex questions directly within construction documents” and “the process is bolstered by custom preprocessing algorithms designed to extract and index information” such as from “unstructured document”; Subbiah, ¶ [0023], [0027], [0029]). However, Subbiah fails to expressly recite wherein the unstructured data includes help video transcripts; removing personally identifiable information from the community question records within the stored digital documents; and generating, from the help documents, document summaries comprising titles and descriptions of the help documents.
The relevance of Chen is described above with relation to claim 5. Regarding claim 11, Chen teaches wherein the unstructured data includes help video transcripts (Discloses that the “domain specific training document is an unstructured data” which can include “video files”, where video files includes help video files, and where “machine-generated text of a content type” is “extracted from the domain-specific training document.” Thus unstructured data also includes help video transcripts.; Chen, ¶ [0132], [0139]); removing personally identifiable information from the community question records within the stored digital documents (“According to the techniques described herein, personal data may be removed from any training dataset that is used to train AI models. The techniques described herein may utilize tools for anonymizing member and customer data. For example, user’s personal data may be redacted and minimized in training datasets for training AI models through delexicalization tools and other privacy enhancing tools for safeguarding user data. The techniques described herein may minimize use of any personal data in training AI models, including removing and replacing personal data.”; Chen, ¶ [0162]); and generating, from the help documents, document summaries comprising titles and descriptions of the help documents (“answers may be generated and tasks summarized based on the data queried and saved” where, in one example, “RFIs” are summarized as “RFI 2—'Missing soffit detail’—Status: Open; RFI 20—'Finish floor elevation’—Status: Open; RFI 60—Basement Slab Level—Status: Open” where RFI corresponds to a title and the description of the RFI is a description; Subbiah, ¶ [0061], [0072]-[0075]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include wherein the unstructured data includes help video transcripts; removing personally identifiable information from the community question records within the stored digital documents; and generating, from the help documents, document summaries comprising titles and descriptions of the help documents. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Regarding claim 14, the rejection of claim 9 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the operations further comprise: generating a question-answer pair... utilizing a large language model (“an LLM is utilized to generate a response based on the contextual data prompt” where the contextual data prompt comprises “the semantically relevant sections (identified in the semantic search) are consolidated/aggregated (e.g., based on relevancy) into a contextual data prompt” alongside the user query, where the generative model is an LLM “trained {to learn...}based on construction data and the response identifies the semantically relevant section(s) {relevant digital documents for the respective software contexts of the computer applications}”; Subbiah, ¶ [0112]-[0113]) tuned based on the stored digital documents, wherein the stored digital documents comprise help documents, community question records, and… [unstructured data] (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records. Further discloses a process including “asking and answering of complex questions directly within construction documents” and “the process is bolstered by custom preprocessing algorithms designed to extract and index information” such as from “unstructured document”; Subbiah, ¶ [0023], [0027], [0029]). However, Subbiah fails to expressly recite generating a question-answer pair from a ground truth document utilizing a large language model tuned based on the stored digital documents wherein the unstructured data includes help video transcripts; generating a predicted response for a sample question from the question-answer pair utilizing the response generator model prompted by the sample question, the ground truth document, and a negative document; and updating the parameters of the response generator model based on a comparison of the predicted response to an answer corresponding to the sample question within the question-answer pair.
The relevance of Chen is described above with relation to claim 5. Regarding claim 14, Chen teaches generating a question-answer pair from a ground truth document utilizing a large language model tuned based on the stored digital documents (Discloses a training data generator to generate input-output pairs, where the “training component 152 uses the manual input-output pairs 104 to train 154 the training data generator 156” as well as obtained “content items 108 by querying the storage system 140, and receiving, from the storage system 140, content items 160” and, in some examples, “the training data generator 156 trained by the training component 152 is an LLM”; Chen, ¶ [0040]-[0041]) wherein the unstructured data includes help video transcripts (Discloses that the “domain specific training document is an unstructured data” which can include “video files”, where video files includes help video files, and where “machine-generated text of a content type” is “extracted from the domain-specific training document.” Thus unstructured data also includes help video transcripts.; Chen, ¶ [0132], [0139]); generating a predicted response for a sample question from the question-answer pair utilizing the response generator model prompted by the sample question, the ground truth document, and a negative document (“In the second stage of the training pipeline, a second machine learning model” also referred to as “pretrained machine learning model 408,” is “fine-tuned to perform one or more domain-specific tasks using the generated supplemental training data” where the generated supplemental training data includes “An input-output pair (e.g., training input 402 and corresponding pseudo label 418, determined by the training data generator 256 described in FIG. 2)” which is “an input with an associated output” and includes “a predicted output and an actual output”; Chen, ¶ [0025], [0060], [0062], [0064]); and updating the parameters of the response generator model based on a comparison of the predicted response to an answer corresponding to the sample question within the question-answer pair (“During each training iteration, the weights are tuned to reduce the amount of error thereby minimizing the differences between (or otherwise converging) a predicted output and an actual output” and “the fine-tuning manager 430 fine-tunes the weights in the pretrained machine learning model 408” where “the value of the pretrained weights in the pretrained weight matrix is adjusted according to an error (e.g., the error 412 determined by the comparator 410 comparing the pseudo label 418 to the predicted output 406).”; Chen, ¶ [0060], [0070]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include generating a question-answer pair from a ground truth document utilizing a large language model tuned based on the stored digital documents wherein the unstructured data includes help video transcripts; generating a predicted response for a sample question from the question-answer pair utilizing the response generator model prompted by the sample question, the ground truth document, and a negative document; and updating the parameters of the response generator model based on a comparison of the predicted response to an answer corresponding to the sample question within the question-answer pair. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Regarding claim 17, the rejection of claim 15 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. However, Subbiah fails to expressly recite wherein the one or more processors are further configured to cause the system to generate the semantically consistent segments by removing personally identifiable information from the stored digital documents utilizing a named entity removal model to replace the personally identifiable information with sanitized text.
The relevance of Chen is described above with relation to claim 5. Regarding claim 17, Chen teaches wherein the one or more processors are further configured to cause the system to generate the semantically consistent segments by removing personally identifiable information from the stored digital documents (“According to the techniques described herein, personal data may be removed from any training dataset that is used to train AI models. The techniques described herein may utilize tools for anonymizing member and customer data. For example, user’s personal data may be redacted and minimized in training datasets for training AI models through delexicalization tools and other privacy enhancing tools for safeguarding user data. The techniques described herein may minimize use of any personal data in training AI models, including removing and replacing personal data.”; Chen, ¶ [0162]) utilizing a named entity removal model to replace the personally identifiable information with sanitized text (Discloses delexicalization including the removal and replacing of “user’s personal data” with sanitized text, where named entity removal is a type of delexicalization, and where said data includes “personal data associated with a user, such as personal information provided by the user to the platform,” which is understood to include a user’s name, a user’s address and other information.; Chen, ¶ [0161], [0162]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include wherein the one or more processors are further configured to cause the system to generate the semantically consistent segments by removing personally identifiable information from the stored digital documents utilizing a named entity removal model to replace the personally identifiable information with sanitized text. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Regarding claim 18, the rejection of claim 15 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the one or more processors are further configured to cause the system to extract the plurality of data segment embeddings by extracting semantically consistent segments from: primary sources comprising document summaries of help documents (Discloses the presentation of “summarized responses with identified sources” where said responses are saved with the vector representation as part of the stored data which is searched based on the stored vectors, and “answers may be generated and tasks summarized based on the data queried and saved” where, in one example, “RFIs” are summarized as “RFI 2—'Missing soffit detail’—Status: Open; RFI 20—'Finish floor elevation’—Status: Open; RFI 60—Basement Slab Level—Status: Open” where RFIs are help document and the RFI title with the description of the RFI is a document summary; Subbiah, ¶ [0056], [0061], [0072]-[0075], [0107], [0109]); and derived sources comprising question-answer pairs generated from... [unstructured data] and community question records (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records. Further discloses a process including “asking and answering of complex questions directly within construction documents” and “the process is bolstered by custom preprocessing algorithms designed to extract and index information” such as from “unstructured document”; Subbiah, ¶ [0023], [0027], [0029]). However, Subbiah fails to expressly recite wherein the unstructured data includes help video transcripts.
The relevance of Chen is described above with relation to claim 5. Regarding claim 18, Chen teaches wherein the unstructured data includes help video transcripts (Discloses that the “domain specific training document is an unstructured data” which can include “video files”, where video files includes help video files, and where “machine-generated text of a content type” is “extracted from the domain-specific training document.” Thus unstructured data also includes help video transcripts.; Chen, ¶ [0132], [0139]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include wherein the unstructured data includes help video transcripts. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]).
Claims 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Balasubramanian as applied to claim 9 above, and further in view of Zhan.
Regarding claim 12, the rejection of claim 9 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. However, Subbiah fails to expressly recite wherein modifying the parameters of the context retrieval model comprises: determining a cosine similarity between a query embedding and a plurality of data segment embeddings extracted from the stored digital documents; and modifying the parameters using a mean squared error function based on the cosine similarity.
Zhan teaches systems and methods for “unsupervised cross-modal Hash retrieval training” (Zhan, ¶ [0001]). Regarding claim 12, Zhan teaches wherein modifying the parameters of the context retrieval model comprises: determining a cosine similarity between a query embedding and a plurality of data segment embeddings extracted from the stored digital documents (“Step 407, the first hash model and the second hash model respectively utilize the mode with small error selected by the other party to perform” backpropagation “and update the network parameters of the first hash model.”; Zhan, ¶ [0024]); and modifying the parameters using a mean squared error function based on the cosine similarity (“calculating cosine similarity on the feature representation, and calculating a mean square error with the pseudo label”; Zhan, ¶ [0024]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Zhan to include wherein modifying the parameters of the context retrieval model comprises: determining a cosine similarity between a query embedding and a plurality of data segment embeddings extracted from the stored digital documents; and modifying the parameters using a mean squared error function based on the cosine similarity. Zhan teaches “an unsupervised cross-modal hashing retrieval method based on noisy label learning. This invention can achieve this by setting up two dual hashing model groups, feeding each other relatively clean pseudo-labels, thus minimizing the model's learning from being misled by noisy pseudo-labels. Ultimately, the model converges to a better position, and its performance on the test dataset is better than other unsupervised cross-modal hashing methods,” as recognized by Zhan. (Zhan, ¶ [0017]).
Claims 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Balasubramanian as applied to claim 9 above, and further in view of Xiong.
Regarding claim 13, the rejection of claim 9 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. However, Subbiah fails to expressly recite wherein the operations further comprise: determining, utilizing a contrastive learning model, a shared weight for a query embedding extracted from the sample query and a plurality of data segment embeddings extracted from data segments of the stored digital documents; and modifying parameters of the context retrieval model utilizing a loss function informed by the shared weight.
Xiong teaches systems and methods for machine learning using “Approximate nearest neighbor Negative Contrastive Learning (ANCE)”. (Xiong, Abstract). Regarding claim 13, Xiong teaches wherein training the context retriever model further comprises: determining, utilizing a contrastive learning model, a shared weight for a query embedding extracted from the sample query and a plurality of data segment embeddings extracted from data segments of the stored digital documents (Authors disclose “Approximate nearest neighbor Negative Contrastive Estimation, (ANCE)” which is contrastive learning, and “ANCE can be used to train any dense retrieval model” described here using a “BERT Siamese/Dual Encoder (shared between q and d),” where q is the query and d is the document, and comprising the shared weight; Xiong, ¶ pg. 4, lines. 22-33); and modifying parameters of the context retrieval model utilizing a loss function informed by the shared weight (“The learning of this representation often follows standard learning to rank (Liu, 2009): Given a query q, a set of relevant document D+ and irrelevant ones D−, find the best θ” can be determined based on equation 2, where, in some examples, “the loss l() can be binary cross entropy (BCE), hinge loss, or negative log likelihood (NLL).”; Xiong, ¶ pg. 2, lines 40-44; Eq. (2)).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Xiong to include wherein the operations further comprise: determining, utilizing a contrastive learning model, a shared weight for a query embedding extracted from the sample query and a plurality of data segment embeddings extracted from data segments of the stored digital documents; and modifying parameters of the context retrieval model utilizing a loss function informed by the shared weight. Acknowledging that “dense retrieval” is a core component “to retrieval relevant information for …extractive/generative QA” and “fact verification” the Xiong indicates ANCE as an improvement on the training of retrieval models in such situations, explaining that “ANCE is orthogonal with those lines of research and focuses on the representation learning for dense retrieval” where the “effectiveness of ANCE on web search, question answering, and in a commercial search environment… nearly matches the accuracy of BERT-based cascade IR pipeline, while being 100x more efficient,” thus providing state of the art retrieval accuracy while reducing processing overhead and improving training convergence, among other benefits, as recognized by Xiong. (Xiong, pg. 8, para. 4).
Claims 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Subbiah and Balasubramanian as applied to claim 15 above, and further in view of Chen and Mahajan (U.S. Pat. App. Pub. No. 2021/0026820, hereinafter Mahajan).
Regarding claim 19, the rejection of claim 15 is incorporated. Subbiah and Balasubramanian disclose all of the elements of the current invention as stated above. Subbiah further discloses wherein the one or more processors are further configured to cause the system to: determine a set of question-answer pairs utilizing a large language model to process the stored digital documents, (Discloses that the user query into “search vectors for a semantic search,” where search vectors are searched against stored vectors, and “an exemplary vector store may include the issues vector database 608A, a specs vector database 608B, and a submittals vector database 608C (collectively referred to as vector store/database 608),” and where “the semantic search is performed within each of the multiple different sections based on the search vectors and the stored vectors. The semantic search identifies the semantically relevant sections of the multiple different sections” and “vector store may be utilized as a dedicated repository for storing embedding vectors that are associated with specification chunks”; Subbiah, ¶ [0111], [0122]-[0123]) wherein the stored digital documents comprise help documents, community question records, and [unstructured data] (the system can “allow customers to ask questions and extract insights from their documents as well as project data such as schedule, issues, RFIs, submittals, etc.” and discloses iterative refinement using documents such as “project performance data, such as issues, RFIs, specifications, takeoff data, locations data, submittals, specifications, schedule, change orders, cost and feedback loops to enhance the models’ understanding and predictive capabilities” where specifications, takeoff data, and change orders are understood as help documents; and issues, RFIs (Requests for Information), and feedback loops are understood as community question records. Further discloses a process including “asking and answering of complex questions directly within construction documents” and “the process is bolstered by custom preprocessing algorithms designed to extract and index information” such as from “unstructured document”; Subbiah, ¶ [0023], [0027], [0029]); and generate the contextual response utilizing the response generator model informed by the subset of question-answer pairs (“an LLM is utilized to generate a response based on the contextual data prompt,” where the contextual data prompt includes “the semantically relevant sections of the multiple different sections (i.e., the semantic search filters the data in the data source to improve the search quality and accuracy)” and the embeddings of “the pre-processed text from the query”; Subbiah, ¶ [0108], [0111], [0113]). However, Subbiah fails to expressly recite wherein the unstructured data includes help video transcripts; [and] generate, from the set of question-answer pairs, a subset of question-answer pairs by removing redundant question-answer pairs using a Levenshtein distance.
The relevance of Chen is described above with relation to claim 5. Regarding claim 19, Chen teaches wherein the unstructured data includes help video transcripts (Discloses that the “domain specific training document is an unstructured data” which can include “video files”, where video files includes help video files, and where “machine-generated text of a content type” is “extracted from the domain-specific training document.” Thus unstructured data also includes help video transcripts.; Chen, ¶ [0132], [0139]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, to incorporate the teachings of Chen to include wherein the unstructured data includes help video transcripts. Chen discloses “Fine-tuning a pre-trained machine learning model” and, more specifically, “adjusting the hyperparameters of the machine learning model that has been pre-trained on domain-neutral data” to adapt the “pre-trained machine learning model to perform a similar task in a domain-specific environment,” which improves performance regarding the domain-specific task and reduces hallucinations, while also “conserv[ing] computing resources such as power and memory,” as recognized by Chen. (Chen, ¶ [0020]-[0023]). However, Subbiah and Chen fail to expressly recite generate, from the set of question-answer pairs, a subset of question-answer pairs by removing redundant question-answer pairs using a Levenshtein distance
Mahajan teaches systems and methods for removing redundant database entries. (Mahajan, ¶ [0001]). Regarding claim 19, Mahajan teaches generate, from the set of question-answer pairs, a subset of question-answer pairs by removing redundant question-answer pairs using a Levenshtein distance (“attribute similarities are computed… on each column and are computed across each pair of rows” including “fuzzy matching comparators…whereby the pair of rows match if they have low Levenshtein distance,” where matching entries are removed as duplicates, and though presented in the context of contact information, the reference clearly indicates that the disclosed embodiments are not limited to such.; Mahajan, ¶ [0018], [0033], [0055]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the two-stage retrieval augmented generation of Subbiah, as modified by the ambiguity resolving pre-processing of Balasubramanian, as modified by the machine learning model fine tuning of Chen, to incorporate the teachings of Mahajan to include generate, from the set of question-answer pairs, a subset of question-answer pairs by removing redundant question-answer pairs using a Levenshtein distance. As explained by Mahajan, deduplication of database entries is well known in the art for, at least, improving search efficiency and conserving storage space. In the context of Subbiah, removing duplicate entries through the use of well-known similarity measures, such as Levenshtein distance, would have been obvious to one of ordinary skill in the art and provide the above well-known benefits, which would speed the search and prompt generation processes, as well as helping to avoid overfitting the data and/or memorizing certain data points due to duplicate entries in the training set, as recognized in the context of Mahajan and Subbiah. (Mahajan, ¶ [0002]-[0004]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kraus (U.S. Pat. App. Pub. No. 2017/0154108) discloses system and method for facilitating machine interpretation of potentially ambiguous input, such as natural language.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Sean E. Serraguard whose telephone number is (313)446-6627. The examiner can normally be reached 07:00-17:00 M-F.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Daniel C. Washburn can be reached at (571) 272-5551. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Sean E Serraguard/Primary Examiner, Art Unit 2657
Prosecution Insights